Literature DB >> 33599254

Subtype-GAN: a deep learning approach for integrative cancer subtyping of multi-omics data.

Hai Yang1, Rui Chen2,3, Dongdong Li1, Zhe Wang1.   

Abstract

MOTIVATION: The discovery of cancer subtyping can help explore cancer pathogenesis, determine clinical actionability in treatment, and improve patients' survival rates. However, due to the diversity and complexity of multi-omics data, it is still challenging to develop integrated clustering algorithms for tumor molecular subtyping.
RESULTS: We propose Subtype-GAN, a deep adversarial learning approach based on the multiple-input multiple-output neural network to model the complex omics data accurately. With the latent variables extracted from the neural network, Subtype-GAN uses consensus clustering and the Gaussian Mixture model to identify tumor samples' molecular subtypes. Compared with other state-of-the-art subtyping approaches, Subtype-GAN achieved outstanding performance on the benchmark data sets consisting of ∼4,000 TCGA tumors from 10 types of cancer. We found that on the comparison data set, the clustering scheme of Subtype-GAN is not always similar to that of the deep learning method AE but is identical to that of NEMO, MCCA, VAE, and other excellent approaches. Finally, we applied Subtype-GAN to the BRCA data set and automatically obtained the number of subtypes and the subtype labels of 1031 BRCA tumors. Through the detailed analysis, we found that the identified subtypes are clinically meaningful and show distinct patterns in the feature space, demonstrating the practicality of Subtype-GAN. AVAILABILITY: The source codes, the clustering results of Subtype-GAN across the benchmark data sets are available at https://github.com/haiyang1986/Subtype-GAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
© The Author(s) 2021. Published by Oxford University Press.

Entities:  

Year:  2021        PMID: 33599254     DOI: 10.1093/bioinformatics/btab109

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  5 in total

1.  MultiGATAE: A Novel Cancer Subtype Identification Method Based on Multi-Omics and Attention Mechanism.

Authors:  Ge Zhang; Zhen Peng; Chaokun Yan; Jianlin Wang; Junwei Luo; Huimin Luo
Journal:  Front Genet       Date:  2022-03-21       Impact factor: 4.599

2.  Msuite2: All-in-one DNA methylation data analysis toolkit with enhanced usability and performance.

Authors:  Lishi Li; Yunyun An; Li Ma; Mengqi Yang; Pengxiang Yuan; Xiaojian Liu; Xin Jin; Yu Zhao; Songfa Zhang; Xin Hong; Kun Sun
Journal:  Comput Struct Biotechnol J       Date:  2022-03-10       Impact factor: 7.271

Review 3.  Unsupervised Multi-Omics Data Integration Methods: A Comprehensive Review.

Authors:  Nasim Vahabi; George Michailidis
Journal:  Front Genet       Date:  2022-03-22       Impact factor: 4.599

Review 4.  Data integration and mechanistic modelling for breast cancer biology: Current state and future directions.

Authors:  Hanyi Mo; Rainer Breitling; Chiara Francavilla; Jean-Marc Schwartz
Journal:  Curr Opin Endocr Metab Res       Date:  2022-06

5.  Identifying Cancer Subtypes Using a Residual Graph Convolution Model on a Sample Similarity Network.

Authors:  Wei Dai; Wenhao Yue; Wei Peng; Xiaodong Fu; Li Liu; Lijun Liu
Journal:  Genes (Basel)       Date:  2021-12-27       Impact factor: 4.096

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.